EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ESpma : A method for assessing biological/non‐biological interfaces using point‐clouds‐based structural features and protein language models

Sarah Nozawa, Kentaro Tomii iD, Yoshinori Fukasawa iD

Protein Science · 2026

DOI: 10.1002/pro.70790 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Protein Science, 2026. Verfasst von Sarah Nozawa und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center for Bioscience Research and Education, Utsunomiya University, Utsunomiya, Japan. Hauptthemen laut MEDLINE: Proteins, Software, Computational Biology, Protein Interaction Mapping. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Agency for Medical Research and Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Distinguishing biological protein–protein interfaces from non‐biological contacts remains an important task in structural biology, particularly as protein complex structures continue to accumulate. Recent advances in protein language models (pLMs) have expanded their use across diverse protein prediction tasks, including sequence‐based protein–protein interaction prediction. Such approaches often pool representations over entire sequences, whereas structure‐based methods commonly rely on more complex graph‐ or geometry‐based integration. We therefore asked how much interface‐relevant information could be extracted by simply pooling pLM embeddings over structurally defined local regions. Here, we revisited biological‐versus‐crystal interface classification as a structurally well‐defined testbed for this question. We developed a framework that compares full‐sequence pooling, interface‐localized pooling of pLM embeddings, and multimodal integration of sequence‐derived embeddings with point‐cloud representations of protein surfaces. On two benchmark datasets, interface‐localized pooling achieved stronger performance than full‐sequence or non‐interacting surface pooling across three pLM backbones. Despite its simplicity, the resulting representation performed within the range of established methods that rely on explicit evolutionary analysis or geometric modeling. Incorporating explicit geometric surface information changed performance slightly, without reaching statistical significance. Because the model is linear, the interface‐level score decomposes exactly into per‐residue contributions, which varied within amino‐acid types. Together, our results indicate that the principal gain arises from localizing pLM embeddings to physically interacting residues, enabling a lightweight and accessible implementation for biological‐versus‐crystal interface classification. Code and scripts are available on GitHub: https://github.com/fukasawa-group/espma .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsSoftwareComputational BiologyProtein Interaction MappingModels, MolecularProtein ConformationLarge Language ModelsDatabases, Protein

Stichwörter der Autor:innen

deep learninginterfacespoint cloudprotein complexesprotein language model

Substanzen

Proteins

Autor:innen und Institutionen

  • Center for Bioscience Research and Education, Utsunomiya University, Utsunomiya, Japan.
  • Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan.

ORCID-Profile: Kentaro Tomii, Yoshinori Fukasawa

Förderung

  • Japan Agency for Medical Research and Development

Zitieren

APA

Nozawa, S., Tomii, K., & Fukasawa, Y. (2026). ESpma : A method for assessing biological/non‐biological interfaces using point‐clouds‐based structural features and protein language models. Protein Science. https://doi.org/10.1002/pro.70790

Vancouver

Nozawa S, Tomii K, Fukasawa Y. ESpma : A method for assessing biological/non‐biological interfaces using point‐clouds‐based structural features and protein language models. Protein Science. 2026. doi:10.1002/pro.70790

BibTeX
@article{Nozawa2026,
  author = {Nozawa, Sarah and Tomii, Kentaro and Fukasawa, Yoshinori},
  title = {ESpma : A method for assessing biological/non‐biological interfaces using point‐clouds‐based structural features and protein language models},
  journal = {Protein Science},
  year = {2026},
  doi = {10.1002/pro.70790}
}
Kostenlos starten →